Public Alpha — v0.1.0-alpha.1

GuardMesh — Public Alpha

Policy enforcement layer for bounded agent actions.

GuardMesh provides a minimal policy evaluation engine
designed for agent systems that require controlled,
governable action execution.

Key capabilities in this release:

• Policy specification and schema validation
• Deterministic policy evaluation engine
• Minimal pack composition for policy bundles
• CLI tooling with JSON output for automation
• Example policy packs
• CI validation and release hygiene workflows

Example CLI usage:

guardmesh policy validate
guardmesh policy inspect
guardmesh evaluate

Project status:

This is an early public alpha release.

APIs, schemas, and CLI behavior may evolve
as the project matures.

Relationship to other modules:

GuardMesh is part of a collection of small open
infrastructure modules for reliable and governable
agent systems, including:

• SkillPulse — detect and heal broken agent skills
• Agent Contracts — structured task delegation
• CapToken — capability tokens for authorization
• TraceForge — portable execution traces
• AgentEvalOps — failure-mode evaluation harness

Feedback and contributions are welcome.